def _get_raw(tmpdir_factory, description=None):
_, fnames = create_mne_dummy_raw(
2, 20000, 100, description=description,
savedir=tmpdir_factory.mktemp('data'), save_format='fif',
random_state=87)
raw = mne.io.read_raw_fif(fnames['fif'], preload=False, verbose=None)
return raw
def test_create_mne_dummy_raw(tmp_path):
n_channels, n_times, sfreq = 2, 10000, 100
raw, fnames = create_mne_dummy_raw(
n_channels, n_times, sfreq, savedir=tmp_path,
save_format=['fif', 'hdf5'])
assert isinstance(raw, mne.io.RawArray)
assert len(raw.ch_names) == n_channels
assert raw.n_times == n_times
assert raw.info['sfreq'] == sfreq
assert isinstance(fnames, dict)
assert os.path.isfile(fnames['fif'])
assert os.path.isfile(fnames['hdf5'])
raw = mne.io.read_raw_fif(fnames['fif'], preload=False, verbose=None)
with h5py.File(fnames['hdf5']) as hf:
_ = np.array(hf['fake_raw'])
def fake_regression_dataset(n_fake_recs, n_fake_chs, fake_sfreq, fake_duration_s):
datasets = []
for i in range(n_fake_recs):
train_or_eval = "eval" if i == 0 else "train"
raw, save_fname = create_mne_dummy_raw(
n_channels=n_fake_chs, n_times=fake_duration_s*fake_sfreq,
sfreq=fake_sfreq, savedir=None)
target = np.random.randint(0, 100, n_classes)
if n_classes == 1:
target = target[0]
fake_descrition = pd.Series(
data=[target, train_or_eval],
index=["target", "session"])
base_ds = BaseDataset(raw, fake_descrition, target_name="target")
datasets.append(base_ds)
dataset = BaseConcatDataset(datasets)
return dataset
